A New Secured Cloud Computing Service: A Case Study of Large Scale Linear Regression

Abstract

Cloud Computing opens new door for the resource-contraints clients to reduce their burden of computation by outsourcing the computation. On the other hand, it is very expensive to compute the large scale linear regression locally but it has great advantages on statistics, economics and data analysis. So, in this paper we are motivated to design a protocol to securely outsourcing of large scale linear regression(LR) to cloud. We use the idea of permutation and padding techniques to hide the original inputs. Compared with previous outsourcing schema, our protocol is efficient with more secured and low complexity.